diff --git a/_init_1.5B_seed42/0/model/model/token_position_embeddings/pp_block/token_embedding/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed42/0/model/model/token_position_embeddings/pp_block/token_embedding/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f1e38959136d8bb09ba3426e3684ed661edb3a9 --- /dev/null +++ b/_init_1.5B_seed42/0/model/model/token_position_embeddings/pp_block/token_embedding/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfe3a567735fb5f4e905d4f30d1443dc2917b309d5931db9b1157a954f37466f +size 131072240 diff --git a/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82ddce9c9bdb546e3b13855825c558b14c09b4a3 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fef8b79d0fe997227de3f3e5652e78b2b5765c0955875c43f0d9dfd3d863ba48 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..89a66a9fbdfee81870b74e188b140e1f39776725 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:272a2565d20d96c3ab9f822df58f237a19f661570eadc26d1dcd85bda14a2c2a +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..116cafa9d14cda664a5397a0a8a08270b7fe7315 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ead070dd91db7ae1ec42a49f91d064ad597f3f9a9344b3bd198c449c21e9871 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2fd138a899d38079a3ff341db38ea0149ac211cc --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8b954fcae4187438deb30b5aa193b7c11c7587bf634ef88d9ddf949fc61d54 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6045f15bfd351f5e9b7d2649b481d1d8e51d0979 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93bf919b81289197a2882779f269b6b6b039d5c79b59830830b3101881b48060 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7aa15764a20242dadc1c9d0d71f3348c4e159b78 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb863ec0e7bd4922ba370f6aa4295c8720d00d911db436a2e58d96df63c32028 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e9025533069d74b80366e14712e7b27707e206bb --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:743ee5c307bdb0cc151f60c05811471c525f883ab6d03d92c4a56999d33dccd4 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4fcfaad332f7caba7149897a5a075220d5b634b5 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3efbaa0203537d9367bb3cc5d7ee05c8d57a8e69a91e7c13c50d1d3185c6a77f +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe73e7f13c3a2494172bb60a7816cc586bc89372 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8730c07879fc1906135c633384bc1808701aa7ee0b49062e471a3d05ef491c12 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/11/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cab4309b1ab77a425f57c07b45cb069cebad7e1e --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f215aed6545682af7eb81c6bfe94638a4a0f35be3b3e774ca9b93907410f6f +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b9d39b6960cacb19443bd722d5fecfedc1b4f2 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/12/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2395a69456ce84640bd22d912d1c63b4cf470231802f9f1ebf2ac43cf50a7c6 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5818077093b07d8d9c7235134ba20f4efac068c5 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a36925e4cbc208147886e8e171575a1f02a9297550d2f86d542a368349ce8db4 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1add923d56a553e188b00a6aafadb82014bdd3cc --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9477a798a07fa1a09f3eeccfdc9e91e35c08ac9ef0cfa25630f621b0824b032d +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0690d0707fb8193bd904d3f463a73a1411699dd0 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e57172dba77c30c0efd1eccee270d8181394827cb0bd386b2978f861a974afc +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7e302cc6ea404f99c31f3bc6d6157ce95146c98b --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7232628246e01043cf6c9722a10eae7939081965c5be426390991880f68bd99 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16403d4ea4998bc8ad928c3a052296bc301dd828 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:492fb387b5d637b2cc83331d21d9eaafc1ac2f887dca905daeda78851311b943 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..847ed7354ff65894c79604dfaa1fb7dc4ee80f36 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd1918915a78603ddf317e86617c2121b896310b0d78255c79c1de1f37757ab2 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3e7f9930fa1c3a1a58435d31dfe268773b7f947c --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02854be812f9e0a8d8d8b33e4c3f8902e8a825683a4cf45f0dd1c4c992e00122 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58d40a823612b3a5dda29234d5ecf25e5a054321 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:debe1e7f9012b0b9992344b778f471f0a39dcfae4676ef08a3f357cad4c03c22 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..497fba6b67a6865534abcfe9ed11b5068df039ea --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2987c94f1cd4c71d6ba3afcc49bc9f345783fe119e37dc4a1a0932d855dda1 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1f7361655c30e55e939e3cb75b466d1f440285c5 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e41a9965a691a5d64fb3b43ab0dd02442f28604513195ec90ae28053b52f037 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..33fac006b58db669b5784f88c99f96807974be1a --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f17b013c347c70b4b2576c35443186ea2c2bcaade37d6ce876565ae448e30a4 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e11f23479a552969811e3f246dc1e4d2f9c3213c --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2222281be90124c7c3d7d99f5dbf21cd8c48e81024a729387ecc840a85ad0347 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/16/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e89608b1fdfbd2f7f2ef919fc60de8ad948b696c --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e479811e311f501e68755ef26d917043a038e200b43183d00d83901c0110f1 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f7af0c03d7a82d66c59a7ea9d0b13b93a156b31 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6812520ee5de6a66c0fc7cbc01089afb6b4bda7d4caf374a6e242aff039af4 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9a793ce4522445d0ea550c3f1a2a76f64c06ea53 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa1bb81b24ac5076e3cad187f1a11f9a52c682f3881d7b77382d3f6438eeb7b7 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e8aea7f4c34c2fc7094d7b5aab7c0be45be8ed64 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e7d114eec311e00f3dc86c272199f7a5dd658bf3e2ddbcb4da8647fb03e0a70 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/17/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c5678049b2df3ade1c1c4151674f32fbe68bbb5b --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0752ef15e09bdbe94628a8892fa393a2cb79e6121a4121a2bdf439c212f45b6a +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7216eba414548caaecc74dded07cad96560a2d20 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d67515a7b6ecf54a784aeeeb6373266e45576ed7b4a4203f5920d95b3aba2ffe +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dec2ccce48afea58a8b50fc0c34836960947f34e --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3e5b41a6a1c5573d18f8d9d87b3b13e8bf2b6a47e764ffda389e70b3364bb59 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..60f0c0cb3b091cd25f024c0f81f2bd2b2ec161d0 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff368faf0090434c79e29c47651cbade35845a42efffa035f9b747a8e84d6fe8 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/18/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a2dd0555a71d267bc3b23d856e6b3a02d2af3da1 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c7c0e7dcfbbb3d0dedb4ce19b257d81e0e64fd05bc6373e24ff2d57d12f9dd4 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff2becb6a8fae6707efc49728a232e923e4fc541 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c9aa6d5f1a0aa2e93bc731defcad4603a3e51c9e322fb561a240fd70847a518 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..88a2ccf2b36f9bf2654a0971f2f3fde820b679cf --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d018f6f29a405515d3a988615b80163d83e6238eb815d763866be6c023e7dcc +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..507d02f94b4109524df118d0cddf7b38dfaedf3f --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bbddf011b89271f00d061e35c8272c44f37c280b83a277fb9d3bdd48a44fd85 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/2/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d0315593203c64ff8fb045c5f08125a0c5ac12fd --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a776f8e6f94700df25a2888a09a79f44d74bca93b59356ee4d12d5b59637f006 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e124537be54ac9860cfda095d06dfb01372ebbae --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dec6d9d556450ff4b188b4502925c256eacfd8b99bc02abaae6d7b84403a46f +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fcae40384f2aa4db34eb2a544063b0a50220315e --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d4559408e3a930b496eeea43c3edf71b0b071600f62dac0d7050f4d07feffb +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1af771ccb6b1e9860b106e66261e2262617da05a --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2931c737486da3c38633f6b56f715218fb191a20cec3d7159ac9e8a7e143a34d +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/20/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c60c84448ad34507fb169b006ade846bb070acd --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8eeaf2935adfd8aba5959809acde79cf7f78d50583f0d09da28fb9f2efe0e96 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f42d13d5d10a0755560a6960ebc10d0648f29c6 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02138e3f1f826db545855f57120e3b5992e4dea7a4b07f1b7d59a197b4e81185 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d8d9152a4d443c22fccd76a18f7d493225372344 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e173dd140e830cafd3dbdb73a45f5521173b592e2620a673c30b99f823803c +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a10e08ff396de9f75a0e5ce2bb658c97de03887c --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6869cd31ef71779ea3b657cb8127851dac1afae20918602c9964dffb823aba +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/21/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ffa28fe95ce2bdde0ecad3a2c22310e419ce52b0 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:558bb5cffa1e54a1473d45f7c81937624455c09974397b0301064bc77e734ccf +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bac145520017f4130064e4b84bdcbbfc57e4fc5d --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3016a5b65b858f4fcca80be21c8bd119e4fc4e35363b7f3dfa39dd2882c6e02a +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b8a1d8be794f057dbf4001b9c42131ebf8b93fb --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51483ffd360fe46746a9aa0c4ef181a5c44d5ba54d594ac87a41358ab5f0d676 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3161434fa40f8f589a20b1f49c639e70aa27d895 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:366b0b8377c898499501d08d202711b88976a7da528bc5e5663508f729f17be6 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/23/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8887561f1e9f5f2828030ec8f670c102763dfe75 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ba418e08610e868ea7d36034ce89d227fb2a427db8ca6605987f33c2ec1368 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dcb943fa10ca69d7ba92e69f7b9e5c930ad23a57 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8845f06a99600fba65581cebc66cf0ad3ac64753ba1dd3909be86be491c705b6 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a58adc83e4bc9d2c3d156a67fc234b3a14175d4 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:727409461a9a81c861d272e21d576f1bbad65e7c7a0db1d5e1577d79c2f717e2 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..974dba29995172fa0d1442f70bae3f1b435ab661 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ab50f7f708e290d37df0c060282bbaad73e7211bfa907cedd9108ac997d2861 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/24/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..93c7ae84a0acaf4f40c5292b743e517ccc669198 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2066d3b162d2ea801da92152e742a0ee3a6d9b7291dc58152445b19f5aa0a66b +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..26063aeeb4fea7f62baa7511ed4da927bc5e8420 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2f3bd5229e62b2f39426fb359f54c67089aed94b74177a00d371e7e01250493 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9113e1601ca7039fe7297358ddd8fd82800cc678 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07c51614b5333451448a67ba62c9e70b8ed1d8200444e381b385d894c2dd44a9 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c6017a46ef3d95a7aff6221c033aba6bdad061e8 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5572e8a3d095271c6052652ffadf9f9134509e6da636cb1845384eb6e4f16f3c +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/25/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4352ba2fc8365d8cb69a3eb384f9fd22a1168df7 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c0a8cf716de40e9c5a493adb2e6a048e60e88de1352bcfe554f479390a681c +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cd71b68528a5efd3d4e0bc70d70f88a03630cd83 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f770007428163e298a5cc9e39db483c850c76b412eab039b16aedc8a2cb02cc +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac796141ec1c606f508ddf942e95ce25901c3ae9 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47c590e810abcad47d54974df2e8c7c0848bb5c781e394f3d0583ae00ddbc92 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cac828f3c9f4534a77a3686d0032458530517816 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b954a6bfa1f604360bf6ce855571439e9e925d7a81aff7ffd2e72e8a15db7c +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a6a8149185c2609a5b461003243ba6a3e1014add --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ac332cd4e4847d0abc8976189ca17c8c468219193988f37f7479f1713c8451b +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8112b6b2fff8122bbc07b562e75ce394c4d80388 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8759918c72eb6fc669cf3b460d30f3a1cd905b10c9513c59b00b50f13c272e1 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f113b601466b717b08aaa9ca2a58ed0c0a183eda --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6eac43589ff8e76a51fe90dc1e552cd3225c9ac37f85b7aff1e61dadb7ba85e +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bcb2eceb6297377bd6e491ca7960450e7d843a0e --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac8aecea0d997e08879bcc538355e3947dd100562cd51b1e411d3b8544e396e +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/27/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2fd7e046bfc677c97d38a9a46578e3daab64fcb2 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46bfc503849a784647ed0721dbb25347b49c28af5cc71e40faeda733090c0fea +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..683470abf7a8e5c1e9d118fa9e6f883c56d98331 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e7adcc9cda3a38891b2af37279fbe3d187c179fc871813a78ab372f7a23e89a +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cea492454c86850197ef38dbc3fb255b88481db8 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b719e349a6a93e251037359bf4f746a81ac892f2bcd6fbe29d8834835ea4cfa +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a083c63b2ea65a4bfce112765d5ecee6417e37e2 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0672a93a666ac0682e615209b62dab93c01dba1cd19d78741cb7836da7d7fc3 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/3/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d1bdb258706afd01a165956a84c991233ca5cde7 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54410f2f8f1e1b7a6b9aacd94efa91e107217b14cb407a021a20257cb04ab4b6 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c24caa154eb124d19e352af7fde476139877e6c7 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:421a23488c1dece4c15c1ce2e02c7197adf0a87fe2e22917ea2ed16702c4916d +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ddaac5873f54403d3ada255c41f0f791bf833702 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a2a62aa399b96a08a0d9f669a58ad1fd337f2dff07db0f4709bf3beac8f865d +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..daf8c51fd58913eda5e8f24ba06a05debac7c488 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5dd6170257b5807369d5e7a8716fdc330f9f31a9cd270c45ef033b505301e91 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..981d191455eb6d130e6d12adca1d88f19e56ee9d --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d208f6586fee23a1fec1723186584ee28e81060dcfb65293cc5ce79dd7f8e22 +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..938bf2f73a8630cfb521e771a2a86390f6223d32 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b658b237992831b76f4ce627ff7fb02c14f4b81115b2c485b272b3c1ba64721c +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8119dfae59c9191197f2c2f1af1ab0c2a88e9810 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3212616b3b0ac58f7edf438ce3d6c1fc7b1d8e12e1e8402fdd9d8da14d487ac4 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..71e041e707c86dbfd1afcf8af496a6a666845df1 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323707582168e0b387f1573259ec882db16cc1a1b4b58b680ce5f66455163287 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ca626efbbefccc831eaa5fbeaa3fd76bc68efbf4 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a31aea18d0e4101c3d372f1be754bd8254d19e81c4571560ce5bdce267980f +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a86348a0e852dc573ed666cea99470e2ff83146 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585df9ed478391aa0da220949f201a9cc31e6e205643644a74e130f4f1facceb +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b6888e91e4a5974b8a7a00339e30ae845dbc7f9 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88a7f8adc9bc1e4b8f0d0ad58996e319241bc2cf1890bcfd354c6561b907ddc4 +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/6/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0e06e81e48c3533a9a20315bcee946ca33355911 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7f446d2301369c3708bbbb7cd18fc12e7e8cd6d1c828451fb64ee24d6f7b21 +size 8388848 diff --git a/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a643bea86e4acd1e5d95b203c975398035e44b82 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:173300fbd31f2c8c3228021f916c9bcbb6bb730b96c88533ce3566017ae90aaf +size 25166192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9790276274bd53001524e08ae27273517eebd569 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b3bc61bdc8d6510b340db83c55eb3e11295087fbd46fcaaaf1805d73443ad37 +size 23068912 diff --git a/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d94f9e2d44f133102a7853bfb90dd9f0f172828a --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:571063fc22a077af3b9c47419587527564fc6c5a7d9149488b0f821281b1c8dd +size 46137656 diff --git a/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b4b10eae70f883daffb696c62ed15c726742ba93 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e933f9076c7b4ddb86690e1fe0812223f3a1cbf5305c806a7d6ab40b056f4f7 +size 4192 diff --git a/_init_1.5B_seed44/0/model/model/token_position_embeddings/pp_block/token_embedding/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/_init_1.5B_seed44/0/model/model/token_position_embeddings/pp_block/token_embedding/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e8de1646b4cc26a8d877063f895720940d2f7e89 --- /dev/null +++ b/_init_1.5B_seed44/0/model/model/token_position_embeddings/pp_block/token_embedding/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566f92b140cc1369c13609f1ef9558f8ed88571eae0451764dc60828dcede703 +size 131072240